kenneth Frank

This is a virtual format for easy accessibility

I am excited to give a workshop July 28-Aug 1 with ICPSR. Hope to see you there! Sensitivity Analysis: Quantifying the Robustness of Inferences to Alternative Factors or Data: web.cvent.com/event/ab4981a1…

check out the 1st hour of my "Sensitivity Analysis for Causal Inference" seminar on YouTube: youtu.be/cIEHaBQRUZk . Join the full seminar Mar. 5-6 to dive deeper into techniques to quantify the robustness of inferences. statisticalhorizons.com/seminars/sensi…

Curious about #sensitivityanalysis in #causalinference? Watch the 1st hour of @kenfrank20’s "Sensitivity Analysis for Causal Inference" seminar on YouTube. Join the full seminar Mar. 5-6 to dive deeper into robust inference techniques. youtu.be/cIEHaBQRUZk

Happy holidays! We have released new versions of the konfound package for statistical sensitivity analysis in R (1.0.2) and in Stata. Full announcement including new features and capabilities is here: konfound-it.org .

And be sure to check out the konfound-it Podcast (notebooklm.google.com/notebook/77e5e…)!

@NateSilver538 Or, to change the inference, one would have to replace about a third of the states (13) with states for which there was no effect of inflation on voting preference. For details, including R and Stata code, go here.

@NateSilver538 konfound-project.shinyapps.io/konfound-it/

So I have some thoughts about that Selzer poll. A lot of thoughts. Excuse any typos, this was put together fast, though we did catch all the "Seltzers". natesilver.net/p/a-shocking-i…

@NateSilver538 Or, to change the inference, one would have to replace about a third of the states (13) with states for which there was no effect of inflation on voting preference. For details, including R and Stata code, go here: konfound-project.shinyapps.io/konfound-it/

@NateSilver538 Nate mentions that there may be confounders that are unobserved. An omitted variable would have to be correlated at about .4 with inflation and with preference for Trump to nullify statistical significance.

39: What Would it Take to Change an Inference? Sensitivity Analysis to Inform Innovation in the Future (16493) cdmcd.co/GwQ7LY #AOM2024

I will be teaching an ICPSR Summer Workshop, "Sensitivity Analysis: Quantifying the Robustness of Inferences to Alternative Factors or Data", web.cvent.com/.../websitePag….... July 8-12, 2024. Hybrid (virtual, FtF in Ann Arbor, MI, with asynchronous access to materials).

Most social scientists need to consider the unobserved conditions that could change an inference.

This workshop is about the statistical tools (R, Stata or the konfound-it app konfound-project.shinyapps.io/konfound-it/) to do just that, quantifying the strength of evidence to inform policy, practice, or general social science.

The workshop is a full 20 instruction hours of instruction including opportunities to adapt to specific models such as mediation, moderation, diff in diff, logistic regression, hazard/cox regression, multilevel models, differential attrition from treatment groups, etc.

Go here to register: web.cvent.com/.../websitePag…...

Group discounts available as well. urldefense.com/.../registrati…...

We will quantify the strength of evidence to inform policy, practice, or social science. Register here. urldefense.com/.../2xSc-y... my bio is here: education.msu.edu/people/frank-k…

Most social scientists need to consider the unobserved conditions that could change an inference. This course is about the statistical tools (R, Stata or the konfound-it app konfound-project.shinyapps.io/konfound-it/) to do just that.